def demo2():
print "rater demo2"
# 读训练集
essays = USTCReader.parseUSTCFile("USTC2011Jan.txt")
trains = []
for essay in essays:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
trains.append(passage)
# 训练打分器
r = CollegeEssayRater()
r.train(trains)
pkfile = open('USTC2011Jan.pkl', 'w')
pickle.dump(trains, pkfile)
pkfile.close()
exit()
# 读测试集
essays = USTCReader.parseUSTCFile("USTC2011Jan-tfidf.txt")
tests = []
for essay in essays:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
tests.append(passage)
# 打分测试
# for p in tests:
# s = r.rate(p)
# p.newscore = s[0]
# print p.id, p.score, s
#
# for p in tests:
# print p.id, p.score, p.newscore
print "SVM......"
r.predict(tests)
pkfile = open('ustc_test.pkl', 'w')
pickle.dump(tests, pkfile)
pkfile.close()
print "demo2 over!!!"
def demo():
print "rater demo"
# 读训练集
essays = USTCReader.parseUSTCFile("essayreader/r1_265.txt")
trains = []
for essay in essays[:]:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
trains.append(passage)
# 训练打分器
r = GeneralEssayRater()
r.train(trains)
pkfile = open('zhang_trains.pkl', 'w')
pickle.dump(trains, pkfile)
pkfile.close()
# 读测试集
essays = USTCReader.parseUSTCFile("USTC2011Jan_Parallel_Zhang.txt")
tests = []
for essay in essays[:]:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
tests.append(passage)
# 打分测试
for p in tests:
s = r.rate(p)
p.newscore = s[0]
print p.id, p.score, s
for p in tests:
print p.id, p.score, p.newscore
pkfile = open('zhang_tests.pkl', 'w')
pickle.dump(tests, pkfile)
pkfile.close()
print "demo over!!!"
def demo():
print "rater demo"
# 读训练集
essays = USTCReader.parseUSTCFile("essayreader/r1_265.txt")
trains = []
for essay in essays[:]:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
trains.append(passage)
# 训练打分器
r = GeneralEssayRater()
r.train(trains)
pkfile = open('zhang_trains.pkl', 'w')
pickle.dump(trains, pkfile)
pkfile.close()
# 读测试集
essays = USTCReader.parseUSTCFile("USTC2011Jan_Parallel_Zhang.txt")
tests = []
for essay in essays[:]:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
tests.append(passage)
# 打分测试
for p in tests:
s = r.rate(p)
p.newscore = s[0]
print p.id, p.score, s
for p in tests:
print p.id, p.score, p.newscore
pkfile = open('zhang_tests.pkl', 'w')
pickle.dump(tests, pkfile)
pkfile.close()
print "demo over!!!"
def demo_one():
content = """At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places. At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places. At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places. At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places."""
# 文章
passage = EssayPassage()
passage.passage = content
passage.title = 'title'
passage.score = 5
passage.id = '1'
passage.reviewerId = 3
passage.content = content
r = SimpleEssayRater()
s = r.rate_by_params(passage)
passage.newscore = s[0]
print passage.id, passage.score, s
print 'OK'
def demo_one():
content = """At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places. At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places. At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places. At present ,more and more students in the college are encouraged to go to the poor places for aid education . This activity is of great benefits for both our college students and the poor places."""
# 文章
passage = EssayPassage()
passage.passage = content
passage.title = 'title'
passage.score = 5
passage.id = '1'
passage.reviewerId = 3
passage.content = content
r = SimpleEssayRater()
s = r.rate_by_params(passage)
passage.newscore = s[0]
print passage.id, passage.score, s
print 'OK'
def generateUSTCFeathers(ustcFilename, outFilename):
essays = USTCReader.parseUSTCFile(ustcFilename)
passages = []
for essay in essays:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
passage.content = essay.content
passages.append(passage)
generatePassageFeathers(passages[:], outFilename)
pkfile = open('ustcpassages_503_lt.pkl', 'w')
pickle.dump(passages, pkfile)
pkfile.close()
def demo_one_sentence():
# 文章
passage = EssayPassage()
passage.passage = 'I am a students.'
passage.title = 'title'
passage.score = 5
passage.id = '1'
passage.reviewerId = 3
passage.content = 'I am a students.'
# 处理文章
essayprepare.processPassage(passage)
extractor = FeatherExtractor()
lf = extractor.extractLangFeather(passage)
passage.lf = lf
cf = extractor.extractContentFeather(passage)
sf = extractor.extractStructureFeather(passage)
print 'OK'
def generateUSTCFeathers(ustcFilename, outFilename):
essays = USTCReader.parseUSTCFile(ustcFilename)
passages = []
for essay in essays:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
passage.content = essay.content
passages.append(passage)
generatePassageFeathers(passages[:], outFilename)
pkfile = open('ustcpassages_503_lt.pkl', 'w')
pickle.dump(passages, pkfile)
pkfile.close()
def demo_one_sentence():
# 文章
passage = EssayPassage()
passage.passage = 'I am a students.'
passage.title = 'title'
passage.score = 5
passage.id = '1'
passage.reviewerId = 3
passage.content = 'I am a students.'
# 处理文章
essayprepare.processPassage(passage)
extractor = FeatherExtractor()
lf = extractor.extractLangFeather(passage)
passage.lf = lf
cf = extractor.extractContentFeather(passage)
sf = extractor.extractStructureFeather(passage)
print 'OK'
def demo2():
essays = USTCReader.parseUSTCFile("USTC2011Jan.txt")
trains = []
for essay in essays:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
passage.content = essay.content
trains.append(passage)
# for p in trains[:30]:
# essayprepare.processPassage(p)
for p in trains[:100]:
# 拆分段落
print "+++++++++++++++++++++++"
paras = essayprepare.para_tokenizer.tokenize(p.content)
pcount1 = len(paras)
scount1 = 0
for para in paras:
sents = essayprepare.markedSentenceTokenize(para)
# for sent in sents:
# print "### ", sent
scount1 += len(sents)
print "-----------------------"
paras = essayprepare.para_tokenizer.tokenize(p.passage)
pcount2 = len(paras)
scount2 = 0
for para in paras:
sents = essayprepare.sent_tokenizer.tokenize(para)
# for sent in sents:
# print "### ", sent
scount2 += len(sents)
if pcount1 != pcount2 or scount1 != scount2:
print p.content
print p.passage
print "\n"
# for i, p in enumerate(trains[:30]):
# for para in p.paragraphs:
# for sent in para.sentences:
# for token in sent.tokens:
# if token.isSpellError:
# print token.token, token.candidates
# for m in essays[i].findMarks():
# if m[0] == 'fm1' or m[0] == 'fm2' or m[0] == 'sw':
# print m
# egrammar_vp1 = "EVP1: {<NN><RB>?<VB>}"
# parser_evp1 = nltk.RegexpParser(egrammar_vp1)
#
# for p in trains[:50]:
# for para in p.paragraphs:
# for sent in para.sentences:
# sentence = [(token.token, token.pos) for token in sent.tokens]
# result = parser_evp1.parse(sentence)
# r = str(result)
# if r.find('EVP1') > 0: print r
print "demo2 over"
demo_one_sentence()
exit()
essays = USTCReader.parseUSTCFile('USTC2011Jan.txt')
print len(essays)
essay = None
for e in essays:
if e.id == "0092":
essay = e
break
# 文章
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
passage.content = essay.content
# 处理文章
essayprepare.processPassage(passage)
# 输出来看看是啥样子
print "PASSAGE========================================="
print passage
print passage.id
print passage.title
print passage.score
print passage.passage
def processEssay(self):
self.browser.clear()
id = unicode(self.lineedit.text())
essay = self.essayDict.get(id)
if not essay:
self.browser.append("<font color=red>%s is not found!</font>" % id)
return
self.browser.append(essay.content)
# 文章
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
# 处理文章
essayprepare.processPassage(passage)
# 输出来看看是啥样子
self.browser.append("PASSAGE=========================================")
self.browser.append(passage.id)
#self.browser.append(passage.title)
self.browser.append(passage.score)
self.browser.append(passage.passage)
self.browser.append(str(len(passage.paragraphs)))
self.browser.append("PARAGRAPHS---------------------------------------")
for para in passage.paragraphs:
self.browser.append(str(para.paragraphNo))
self.browser.append(para.paragraph)
for sent in para.sentences:
self.browser.append(str(sent.sentenceNo))
self.browser.append(str(sent.paragraphSentenceNo))
self.browser.append(sent.sentence)
tokens = [token.token for token in sent.tokens]
tags = [token.pos for token in sent.tokens]
lemmas = [token.lemma for token in sent.tokens]
stems = [token.stem for token in sent.tokens]
levels = [token.level for token in sent.tokens]
nos = [token.tokenNo for token in sent.tokens]
sentNos = [token.sentenceTokenNo for token in sent.tokens]
paraNos = [token.paragraphTokenNo for token in sent.tokens]
errorTokens = [token.token for token in sent.tokens if token.isSpellError]
if not sent.canParsed:
self.browser.append("<font color=red>SENTENCE ERROR</font>")
self.browser.append("<font color=red>SPELLERROR %s</font>" % str(errorTokens))
self.browser.append(str(tokens))
self.browser.append(str(tags))
self.browser.append(str(lemmas))
self.browser.append(str(stems))
self.browser.append(str(levels))
self.browser.append(str(sentNos))
self.browser.append(str(paraNos))
self.browser.append(str(nos))
self.browser.append(str(sent.tokenCount))
self.browser.append(str(sent.wordCount))
self.browser.append(str(sent.realWordCount))
self.browser.append(u"三元词组" + ' ' + str(passage.trigrams))
e = FeatherExtractor()
# 提取语言特征
languageFeather = e.extractLangFeather(passage)
print u"词次总数", languageFeather.tokenCount
print u"单词总数", languageFeather.wordCount
print u"词形总数", languageFeather.wordTypeCount
print u"词元总数", languageFeather.wordLemmaCount
print u"介词个数", languageFeather.prepositionCount
print u"介词比例", languageFeather.prepositionRatio
print u"介词使用", languageFeather.prepositionUse
print u"定冠词个数", languageFeather.definiteArticleCount
print u"定冠词比例", languageFeather.definiteArticleRatio
print u"定冠词使用", languageFeather.definiteArticleUse
# 提取结构特征
#structureFeather = e.extractStructureFeather(passage)
#generateUSTCFeathers('USTC2011Jan.txt', 'USTCFeathers_503.txt')
print "...OVER"
def processEssay(self):
self.browser.clear()
id = unicode(self.lineedit.text())
essay = self.essayDict.get(id)
if not essay:
self.browser.append("<font color=red>%s is not found!</font>" % id)
return
self.browser.append(essay.content)
# 文章
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
# 处理文章
essayprepare.processPassage(passage)
# 输出来看看是啥样子
self.browser.append("PASSAGE=========================================")
self.browser.append(passage.id)
#self.browser.append(passage.title)
self.browser.append(passage.score)
self.browser.append(passage.passage)
self.browser.append(str(len(passage.paragraphs)))
self.browser.append(
"PARAGRAPHS---------------------------------------")
for para in passage.paragraphs:
self.browser.append(str(para.paragraphNo))
self.browser.append(para.paragraph)
for sent in para.sentences:
self.browser.append(str(sent.sentenceNo))
self.browser.append(str(sent.paragraphSentenceNo))
self.browser.append(sent.sentence)
tokens = [token.token for token in sent.tokens]
tags = [token.pos for token in sent.tokens]
lemmas = [token.lemma for token in sent.tokens]
stems = [token.stem for token in sent.tokens]
levels = [token.level for token in sent.tokens]
nos = [token.tokenNo for token in sent.tokens]
sentNos = [token.sentenceTokenNo for token in sent.tokens]
paraNos = [token.paragraphTokenNo for token in sent.tokens]
errorTokens = [
token.token for token in sent.tokens if token.isSpellError
]
if not sent.canParsed:
self.browser.append(
"<font color=red>SENTENCE ERROR</font>")
self.browser.append("<font color=red>SPELLERROR %s</font>" %
str(errorTokens))
self.browser.append(str(tokens))
self.browser.append(str(tags))
self.browser.append(str(lemmas))
self.browser.append(str(stems))
self.browser.append(str(levels))
self.browser.append(str(sentNos))
self.browser.append(str(paraNos))
self.browser.append(str(nos))
self.browser.append(str(sent.tokenCount))
self.browser.append(str(sent.wordCount))
self.browser.append(str(sent.realWordCount))
self.browser.append(u"三元词组" + ' ' + str(passage.trigrams))
e = FeatherExtractor()
# 提取语言特征
languageFeather = e.extractLangFeather(passage)
print u"词次总数", languageFeather.tokenCount
print u"单词总数", languageFeather.wordCount
print u"词形总数", languageFeather.wordTypeCount
print u"词元总数", languageFeather.wordLemmaCount
print u"介词个数", languageFeather.prepositionCount
print u"介词比例", languageFeather.prepositionRatio
print u"介词使用", languageFeather.prepositionUse
print u"定冠词个数", languageFeather.definiteArticleCount
print u"定冠词比例", languageFeather.definiteArticleRatio
print u"定冠词使用", languageFeather.definiteArticleUse
# 提取结构特征
#structureFeather = e.extractStructureFeather(passage)
#generateUSTCFeathers('USTC2011Jan.txt', 'USTCFeathers_503.txt')
print "...OVER"
def demo_crossvalidate_zhang():
print "rater demo_crossvalidate_zhang"
# 读训练集
essays = USTCReader.parseUSTCFile("essayreader/r1_265.txt")
trains = []
for essay in essays[:]:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
trains.append(passage)
# 读测试集
essays = USTCReader.parseUSTCFile("USTC2011Jan_Parallel_Zhang.txt")
tests = []
for essay in essays[:]:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
tests.append(passage)
passages = []
passages.extend(trains)
passages.extend(tests)
random.shuffle(passages)
scoreEssays = {}
for p in passages:
if p.score < 35: p.score = 35
label = (int(p.score) + 2) / 5 - 4
if label < 3:
label = 3
#continue
if label > 14: label = 14
p.label = label
if label not in scoreEssays:
scoreEssays[label] = []
scoreEssays[label].append(p)
# cross validate
ps = [[], [], [], [], []]
left = []
for k, v in scoreEssays.items():
print k
print len(v)
if len(v) > 5:
s = len(v) / 5
for i in range(5):
ps[i].extend(v[i*s: (i+1)*s])
left.extend(v[5*s:])
else:
left.extend(v)
for j in range(len(left)):
ps[j % 5].append(left[j])
print "data sets: "
for v in ps:
print len(v)
for i in range(5):
trains = []
tests = []
for j in range(5):
if i == j:
tests.extend(ps[j])
else:
trains.extend(ps[j])
r = CollegeEssayRater()
r.train(trains)
for p in tests:
s = r.rate(p)
p.newscore = s[0]
print p.id, p.score, s
s1 = []
s2 = []
for p in passages:
if p.label < 3: continue
s1.append(int(p.score))
s2.append(p.newscore)
print p.id, p.score, p.endogScore, int(round(p.newscore)), p.score - int(round(p.newscore)), \
p.lsaScore, p.lsaSimilarity, p.lsaSimilarityAll, p.lf.tokenCount, \
p.lf.sentenceLengthAverage, p.lf.wordLengthAverage, p.lf.noneStopWordLengthAverage, \
p.lf.nounRatio, p.lf.verbRatio, p.lf.adjRatio, p.lf.sentenceLengthSD, p.offsetRatio, \
p.lf.aclWordCount, p.lf.aclWordRatio
print scistats.pearsonr(s1, s2)
pkfile = open('zhang_all.pkl', 'w')
pickle.dump(passages, pkfile)
pkfile.close()
print "demo_crossvalidate over!!!"
def demo2():
essays = USTCReader.parseUSTCFile("USTC2011Jan.txt")
trains = []
for essay in essays:
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
passage.content = essay.content
trains.append(passage)
# for p in trains[:30]:
# essayprepare.processPassage(p)
for p in trains[:100]:
# 拆分段落
print "+++++++++++++++++++++++"
paras = essayprepare.para_tokenizer.tokenize(p.content)
pcount1 = len(paras)
scount1 = 0
for para in paras:
sents = essayprepare.markedSentenceTokenize(para)
# for sent in sents:
# print "### ", sent
scount1 += len(sents)
print "-----------------------"
paras = essayprepare.para_tokenizer.tokenize(p.passage)
pcount2 = len(paras)
scount2 = 0
for para in paras:
sents = essayprepare.sent_tokenizer.tokenize(para)
# for sent in sents:
# print "### ", sent
scount2 += len(sents)
if pcount1 != pcount2 or scount1 != scount2:
print p.content
print p.passage
print "\n"
# for i, p in enumerate(trains[:30]):
# for para in p.paragraphs:
# for sent in para.sentences:
# for token in sent.tokens:
# if token.isSpellError:
# print token.token, token.candidates
# for m in essays[i].findMarks():
# if m[0] == 'fm1' or m[0] == 'fm2' or m[0] == 'sw':
# print m
# egrammar_vp1 = "EVP1: {<NN><RB>?<VB>}"
# parser_evp1 = nltk.RegexpParser(egrammar_vp1)
#
# for p in trains[:50]:
# for para in p.paragraphs:
# for sent in para.sentences:
# sentence = [(token.token, token.pos) for token in sent.tokens]
# result = parser_evp1.parse(sentence)
# r = str(result)
# if r.find('EVP1') > 0: print r
print "demo2 over"
demo_one_sentence()
exit()
essays = USTCReader.parseUSTCFile('USTC2011Jan.txt')
print len(essays)
essay = None
for e in essays:
if e.id == "0092":
essay = e
break
# 文章
passage = EssayPassage()
passage.passage = essay.cleanContent()
passage.title = essay.title
passage.score = essay.score
passage.id = essay.id
passage.reviewerId = essay.reviewerId
passage.content = essay.content
# 处理文章
essayprepare.processPassage(passage)
# 输出来看看是啥样子
print "PASSAGE========================================="
print passage
print passage.id
print passage.title
print passage.score
print passage.passage